© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120956
    Prev
    Next
    INDEX
    Explanations

    definitively

    np_acts-logits-general · gemini-2.5-flash-lite

    service jobs], I have consistently demonstrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شق
    0.54
     peligros
    0.52
     tuleb
    0.50
     hôtel
    0.50
     herramientas
    0.49
     Folklore
    0.49
     énorme
    0.48
    ম
    0.46
     narzęd
    0.46
    서울특별시
    0.46
    POSITIVE LOGITS
     to
    0.64
     Schmid
    0.47
     screened
    0.47
     weathered
    0.45
     пра
    0.45
     Carol
    0.44
     зали
    0.44
     संरक्षित
    0.44
     definitively
    0.43
     мати
    0.43
    Activations Density 0.000%

    No Known Activations